Abstract
Cardiomyopathy is one of the most serious public health threats. The precise structural and functional cardiac measurement is an essential step for clinical diagnosis and follow-up treatment planning. Cardiologists are often required to draw endocardial and epicardial contours of the left ventricle (LV) manually in routine clinical diagnosis or treatment planning period. This task is time-consuming and error-prone. Therefore, it is necessary to develop a fully automated end-to-end semantic segmentation method on cardiac magnetic resonance (CMR) imaging datasets. However, due to the low image quality and the deformation caused by heartbeat, there is no effective tool for fully automated end-to-end cardiac segmentation task. In this work, we propose a multi-scale segmentation network (MSSN) for left ventricle segmentation. It can effectively learn myocardium and blood pool structure representations from 2D short-axis CMR image slices in a multi-scale way. Specifically, our method employs both parallel and serial of dilated convolution layers with different dilation rates to capture multi-scale semantic features. Moreover, we design graduated up-sampling layers with subpixel layers as the decoder to reconstruct lost spatial information and produce accurate segmentation masks. We validated our method using 164 T1 Mapping CMR images and showed that it outperforms the advanced convolutional neural network (CNN) models. In validation metrics, we archived the Dice Similarity Coefficient (DSC) metric of 78.96%.
Highlights
Cardiomyopathy is one kind of serious cardiac diseases which major cause of death in the world wild
To verify the performance on left ventricle (LV) segmentation of our proposed method, we apply our model compare with other advanced segmentation methods with the same datasets and experimental settings
The original T1 Mapping cardiac magnetic resonance (CMR) image is displayed in the first column
Summary
Cardiomyopathy is one kind of serious cardiac diseases which major cause of death in the world wild. Ngo et al [Ngo and Carneiro (2013)] use restricted Boltzmann machines (RBMs) to obtain segmentation results on a small LV dataset Their method is semi-automated that requires user input. Fu et al [Fu, Xu, Zhang et al (2019)] proposed a noise-resistant superpixel segmentation method for hyperspectral images segmentation These methods design different model structures and directly learn the optimal network parameters for label prediction. We propose and validate a new convolutional neural network architecture for LV segmentation, which can automatically train and inference on CMR image datasets. We validated our method using 164 CMR images and showed that it outperforms the advanced convolutional neural network (CNN) models
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Information Hiding and Privacy Protection
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
